set_rule

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare destructiveHint=true and readOnlyHint=false, and the description adds substantial behavior beyond them: the merge is provisional ('Both rules are on until the user decides'), approval happens on the Feedback board, and user-authored rules are protected. It still doesn't say whether removal is reversible or how conflicts between simultaneous edits resolve, so it stops short of a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the verb set and the most important workflow constraint before drifting into the long check specification, which is a dense tail. Every clause carries information, but the appended enumeration of check semantics makes it read as one long run-on paragraph rather than clearly segmented guidance.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a nine-parameter mutation tool with a nested object and no output schema, the description covers the tricky parts: the merge/approval lifecycle, the per-area cap, and the by_user protection. What is missing is minor mechanical detail (how to identify a 'full' area, what the agent sees after a merge is pending), so it is close to complete without being exhaustive.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description earns extra by decoding the nested check object the schema only sketches as '{kind, target, tolerance, max, floor}' — it enumerates the four kinds with units and defaults (LUFS target/tolerance, pause max/floor, dBTP peak). It also adds hard limits not present in the schema (220 chars for text, 600 for details, 10 rules per area).

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The opening clause names a precise set of verbs (add, change, turn off, remove) against a precisely scoped resource (one learned rule), and the scope limit 'one' is explicit. It also cross-references siblings by naming check_edit and implicitly contrasting with get_rules, so an agent can place it without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives concrete when-to-use guidance and an alternative path: 'sharpen a rule before you add one', and 'When an area is full, add the new rule with merge_into (the closest rule) and merged'. It also states an explicit prohibition ('Never change a rule the user wrote (by_user) without asking first'), which is exactly the kind of routing/eligibility rule an agent needs.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.